Großbuchstaben mit span-Klasse versehen (RegEx für Umlaute)

function caps( $text )
{
    // Tokenize; see smartypants.php
    $tokens = _TokenizeHTML($text);    
    $result = array();
    $in_skipped_tag = false;
    
    $cap_finder = "/(
            (\b[A-Z\d]*			# Group 2: Any amount of caps and digits
            [A-Z]\d*[A-Z]		# A cap string must at least include two caps (but they can have digits between them)
            [A-Z\d]*\b)			# Any amount of caps and digits
            | (\b[A-Z]+\.\s?	# OR: Group 3: Some caps, followed by a '.' and an optional space
            (?:[A-Z]+\.\s?)+)	# Followed by the same thing at least once more
            (?:\s|\b|$))/x";
    
    $tags_to_skip_regex = "/<(\/)?(?:pre|code|kbd|script|math)[^>]*>/i";
    
    foreach ($tokens as $token)
    {
        if ( $token[0] == "tag" )
        {
            // Don't mess with tags.
            $result[] = $token[1];
            $close_match = preg_match($tags_to_skip_regex, $token[1]);            
            if ( $close_match )
            {
                $in_skipped_tag = true;
            }
            else
            {
                $in_skipped_tag = false;
            }
        }
        else
        {
            if ( $in_skipped_tag )
            {
                $result[] = $token[1];
            }
            else
            {
                $result[] = preg_replace_callback($cap_finder, _cap_wrapper, $token[1]);
            }
        }
    }        
    return join("", $result);    
}

if (!function_exists('_TokenizeHTML')) :
function _TokenizeHTML($str) {
#   Parameter:  String containing HTML markup.
#   Returns:    An array of the tokens comprising the input
#               string. Each token is either a tag (possibly with nested,
#               tags contained therein, such as <a href="<MTFoo>">, or a
#               run of text between tags. Each element of the array is a
#               two-element array; the first is either 'tag' or 'text';
#               the second is the actual value.
#
#
#   Regular expression derived from the _tokenize() subroutine in 
#   Brad Choate's MTRegex plugin.
#   <http://www.bradchoate.com/past/mtregex.php>
#
	$index = 0;
	$tokens = array();


	$match = '(?s:<!(?:--.*?--\s*)+>)|'.	# comment
			 '(?s:<\?.*?\?>)|'.				# processing instruction
			 								# regular tags
			 '(?:<[/!$]?[-a-zA-Z0-9:]+\b(?>[^"\'>]+|"[^"]*"|\'[^\']*\')*>)';


	$parts = preg_split("{($match)}", $str, -1, PREG_SPLIT_DELIM_CAPTURE);


	foreach ($parts as $part) {
		if (++$index % 2 && $part != '') 
			$tokens[] = array('text', $part);
		else
			$tokens[] = array('tag', $part);
	}
	return $tokens;
}
endif;